Head pose-free eye gaze prediction for driver attention study

Abstract

Driver's gaze direction is an indicator of driver state and plays a significantly role in driving safety. Traditional gaze zone estimation methods based on eye model have disadvantages due to the vulnerability under large head movement. Different from these methods, an appearance-based head pose-free eye gaze prediction method is proposed in this paper, for driver gaze zone estimation under free head movement. To achieve this goal, a gaze zone classifier is trained with head vectors and eye image features by random forest. The head vector is calculated by Pose from Orthography and Scaling with ITerations (POSIT) where a 3D face model is combined with facial landmark detection. And the eye image features are derived from eye images which extracted through eye region localization. These features are presented as the combination of sparse coefficients by sparse encoding with eye image dictionary, having good potential to carry information of the eye images. Experimental results show that the proposed method is applicable in real driving environment.